{"id":"https://openalex.org/W4394926269","doi":"https://doi.org/10.1186/s12859-024-05775-w","title":"TrieDedup: a fast trie-based deduplication algorithm to handle ambiguous bases in high-throughput sequencing","display_name":"TrieDedup: a fast trie-based deduplication algorithm to handle ambiguous bases in high-throughput sequencing","publication_year":2024,"publication_date":"2024-04-18","ids":{"openalex":"https://openalex.org/W4394926269","doi":"https://doi.org/10.1186/s12859-024-05775-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/38637756"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-024-05775-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05775-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05775-w","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05775-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101991465","display_name":"Jianqiao Hu","orcid":"https://orcid.org/0000-0003-2867-0842"},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianqiao Hu","raw_affiliation_strings":["Department of Biology, University of Washington, Seattle, WA, USA","Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046297681","display_name":"Sai Luo","orcid":"https://orcid.org/0000-0002-7362-5445"},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Sai Luo","raw_affiliation_strings":["Harvard Medical School, Boston, MA, USA","Howard Hughes Medical Institute, Boston Children's Hospital, Boston, MA, USA","Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA, USA","School of Basic Medical Science, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Howard Hughes Medical Institute, Boston Children's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I1344073410"]},{"raw_affiliation_string":"Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113"]},{"raw_affiliation_string":"School of Basic Medical Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068104219","display_name":"Ming Tian","orcid":"https://orcid.org/0000-0003-4350-3380"},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Tian","raw_affiliation_strings":["Harvard Medical School, Boston, MA, USA","Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044129875","display_name":"Adam Yongxin Ye","orcid":"https://orcid.org/0000-0002-1542-0740"},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adam Yongxin Ye","raw_affiliation_strings":["Harvard Medical School, Boston, MA, USA. yeyx2626@gmail.com","Howard Hughes Medical Institute, Boston Children's Hospital, Boston, MA, USA. yeyx2626@gmail.com","Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA, USA. yeyx2626@gmail.com","Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA. yeyx2626@gmail.com","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Howard Hughes Medical Institute, Boston Children's Hospital, Boston, MA, USA. yeyx2626@gmail.com","institution_ids":["https://openalex.org/I1344073410"]},{"raw_affiliation_string":"Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA, USA. yeyx2626@gmail.com","institution_ids":["https://openalex.org/I1288882113"]},{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044129875"],"corresponding_institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I1344073410","https://openalex.org/I136199984"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.16,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46462351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"25","issue":"1","first_page":"154","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.5893999934196472,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.5893999934196472,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.05260000005364418,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8040181398391724},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.787408709526062},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6111261248588562},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5734780430793762},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.46534714102745056},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4494839608669281},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.42187532782554626},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4202967882156372},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41304242610931396},{"id":"https://openalex.org/keywords/barcode","display_name":"Barcode","score":0.41277238726615906},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32488101720809937},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1761513352394104},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14844349026679993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040181398391724},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.787408709526062},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6111261248588562},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5734780430793762},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.46534714102745056},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4494839608669281},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.42187532782554626},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4202967882156372},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41304242610931396},{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.41277238726615906},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32488101720809937},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1761513352394104},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14844349026679993},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-024-05775-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05775-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05775-w","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38637756","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38637756","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11025179","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11025179","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11025179/pdf/12859_2024_Article_5775.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:c0d65baf08eb4d6dbd2a0aafa4959b6d","is_oa":false,"landing_page_url":"https://doaj.org/article/c0d65baf08eb4d6dbd2a0aafa4959b6d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 25, Iss 1, Pp 1-13 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-024-05775-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05775-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05775-w","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3058190383","display_name":"Mechanisms That Control Antigen Receptor Variable Region Exon Assembly","funder_award_id":"5r01ai020047-41","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3599394851","display_name":"Children's Hospital Boston - to accelerate testing of candidate HIV vaccines in appropriate pre-clinical models","funder_award_id":"INV-021989","funder_id":"https://openalex.org/F4320306137","funder_display_name":"Bill and Melinda Gates Foundation"},{"id":"https://openalex.org/G5325504816","display_name":"Project 2. Animal studies to elucidate the optimal sequence of Env immunogens for induction of distal MPER bnAbs","funder_award_id":"5p01ai138211-04","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6150096993","display_name":"Mechanisms that Regulate Antibody Class Switch Recombination and Somatic Hypermutation","funder_award_id":"4r37ai077595-16","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6577356133","display_name":null,"funder_award_id":"P01 AI138211","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"}],"funders":[{"id":"https://openalex.org/F4320306082","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90"},{"id":"https://openalex.org/F4320306137","display_name":"Bill and Melinda Gates Foundation","ror":"https://ror.org/0456r8d26"},{"id":"https://openalex.org/F4320309356","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394926269.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2108234281","https://openalex.org/W2117608012","https://openalex.org/W2119923823","https://openalex.org/W2151558930","https://openalex.org/W2319185332","https://openalex.org/W2335547104","https://openalex.org/W2472930439","https://openalex.org/W2523787414","https://openalex.org/W2952109315","https://openalex.org/W2996575833","https://openalex.org/W2998672854","https://openalex.org/W3021435052","https://openalex.org/W4313251644"],"related_works":["https://openalex.org/W2046569047","https://openalex.org/W2186419898","https://openalex.org/W3092534692","https://openalex.org/W2370961680","https://openalex.org/W2278452282","https://openalex.org/W4300504307","https://openalex.org/W207628907","https://openalex.org/W2740229587","https://openalex.org/W1786707430","https://openalex.org/W2159312398"],"abstract_inverted_index":{"BACKGROUND:":[0],"High-throughput":[1],"sequencing":[2,164,178],"is":[3,8],"a":[4,138],"powerful":[5],"tool":[6],"that":[7,125,170],"extensively":[9],"applied":[10],"in":[11,28,34,114],"biological":[12],"studies.":[13],"However,":[14],"sequencers":[15],"may":[16,50,149],"produce":[17],"low-quality":[18],"bases,":[19,23],"leading":[20],"to":[21,54,82,131,177],"ambiguous":[22,55,90,174],"'N's.":[24],"PCR":[25,151],"duplicates":[26],"introduced":[27],"library":[29],"preparation":[30],"are":[31],"conventionally":[32],"removed":[33],"genomics":[35],"studies,":[36],"and":[37,57,71,84,93,123,157],"several":[38],"deduplication":[39],"tools":[40,60],"have":[41],"been":[42],"developed":[43],"for":[44,173],"this":[45],"purpose.":[46],"Two":[47],"identical":[48],"reads":[49,129],"appear":[51],"different":[52],"due":[53,176],"bases":[56,175],"the":[58,76,97,118,121],"existing":[59],"cannot":[61],"address":[62],"'N's":[63],"correctly":[64],"or":[65,154],"efficiently.":[66],"RESULTS:":[67],"Here":[68],"we":[69],"proposed":[70],"implemented":[72],"TrieDedup,":[73],"which":[74],"uses":[75],"trie":[77],"(prefix":[78],"tree)":[79],"data":[80],"structure":[81],"compare":[83],"store":[85],"sequences.":[86,101],"TrieDedup":[87,126,147],"can":[88,127,171],"handle":[89],"base":[91],"'N's,":[92],"efficiently":[94],"deduplicate":[95,128],"at":[96,137],"level":[98],"of":[99,120,140,161],"raw":[100],"We":[102,116],"also":[103],"reduced":[104],"its":[105,167],"memory":[106,143],"usage":[107],"by":[108,111],"approximately":[109],"20%":[110],"implementing":[112],"restrictedDict":[113],"Python.":[115],"benchmarked":[117],"performance":[119],"algorithm":[122,148,169],"showed":[124],"up":[130],"270-fold":[132],"faster":[133],"than":[134],"pairwise":[135],"comparison":[136],"cost":[139],"32-fold":[141],"higher":[142],"usage.":[144],"CONCLUSIONS:":[145],"The":[146],"facilitate":[150],"deduplication,":[152],"barcode":[153],"UMI":[155],"assignment,":[156],"repertoire":[158],"diversity":[159],"analysis":[160],"large-scale":[162],"high-throughput":[163],"datasets":[165],"with":[166],"ultra-fast":[168],"account":[172],"errors.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
